Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    descriptive adjectives

    np_max-act · gemini-2.0-flash

    The neuron is triggered by the placeholder token “NAME_1,” i.e. it spots that specific NAME_# placeholder whenever it appears.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -tra
    -0.07
     业
    -0.07
    _joint
    -0.07
     Hast
    -0.07
    Equ
    -0.07
    _BT
    -0.06
    	answer
    -0.06
    廣
    -0.06
     TP
    -0.06
    Hu
    -0.06
    POSITIVE LOGITS
    ?action
    0.07
    ження
    0.06
    >');↵↵
    0.06
     amort
    0.06
     політи
    0.06
     teleport
    0.06
    (orig
    0.06
     ilişk
    0.06
    ucking
    0.06
     drink
    0.06
    Act Density 0.076%

    No Known Activations